Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2632 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0377. Min Range: -1.0377

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1256094 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9268. Min Act: -0.0000

Data Index: 678089 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1302699 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7281. Min Act: -0.0000

Data Index: 727846 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7220. Min Act: -0.0000

Data Index: 940970 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7878. Min Act: -0.0000

Data Index: 140337 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1428216 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1885288 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6898. Min Act: -0.0000

Data Index: 241181 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1723189 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6402. Min Act: -0.0000

Data Index: 416271 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1648519 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6548. Min Act: -0.0000

Data Index: 147324 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1757885 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6264. Min Act: -0.0000

Data Index: 758828 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7064. Min Act: -0.0000

Data Index: 434120 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1958377 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7025. Min Act: -0.0000

Data Index: 165519 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1399134 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.6465. Min Act: -0.0000

Data Index: 394206 (The Pile)

Max Activating Token Index: 138